742 citations · 2.5k across the 92 of their papers we have counts for
96 papers
ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation
Ziyang Mai, Yu-Wing Tai
Text-to-video generation has advanced rapidly, yet preserving a character's holistic appearance from a single reference image remains challenging, particularly when the character u…
UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention
Yuyao Zhang, Yu-Wing Tai
Ultra-high-resolution text-to-image generation is increasingly vital for applications requiring fine-grained textures and global structural fidelity, yet state-of-the-art text-to-i…
PS-ReID: Advancing Person Re-Identification and Precise Segmentation with Multimodal Retrieval
Jincheng Yan, Yun Wang, Xiaoyan Luo +1
Person re-identification (ReID) plays a critical role in applications such as security surveillance and criminal investigations. Most traditional image-based ReID methods face chal…
Scene-Generalizable Interactive Segmentation of Radiance Fields
Songlin Tang, Wenjie Pei, Xin Tao +3
Existing methods for interactive segmentation in radiance fields entail scene-specific optimization and thus cannot generalize across different scenes, which greatly limits their a…
Feature Decoupling-Recycling Network for Fast Interactive Segmentation
Huimin Zeng, Weinong Wang, Xin Tao +3
Recent interactive segmentation methods iteratively take source image, user guidance and previously predicted mask as the input without considering the invariant nature of the sour…
Cascade-DETR: Delving into High-Quality Universal Object Detection
Mingqiao Ye, Lei Ke, Siyuan Li +4
Object localization in general environments is a fundamental part of vision systems. While dominating on the COCO benchmark, recent Transformer-based detection methods are not comp…
Segment Anything Meets Point Tracking
Frano Rajič, Lei Ke, Yu-Wing Tai +3
The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, enabled by efficient point-centric annotation and prompt-based models. Whi…
UniBoost: Unsupervised Unimodal Pre-training for Boosting Zero-shot Vision-Language Tasks
Yanan Sun, Zihan Zhong, Qi Fan +2
Large-scale joint training of multimodal models, e.g., CLIP, have demonstrated great performance in many vision-language tasks. However, image-text pairs for pre-training are restr…
Segment Anything in High Quality
Lei Ke, Mingqiao Ye, Martin Danelljan +4
The recent Segment Anything Model (SAM) represents a big leap in scaling up segmentation models, allowing for powerful zero-shot capabilities and flexible prompting. Despite being…
Registering Neural Radiance Fields as 3D Density Images
Han Jiang, Ruoxuan Li, Haosen Sun +2
No significant work has been done to directly merge two partially overlapping scenes using NeRF representations. Given pre-trained NeRF models of a 3D scene with partial overlappin…
Distill Gold from Massive Ores: Bi-level Data Pruning towards Efficient Dataset Distillation
Yue Xu, Yong-Lu Li, Kaitong Cui +4
Data-efficient learning has garnered significant attention, especially given the current trend of large multi-modal models. Recently, dataset distillation has become an effective a…
Deceptive-NeRF/3DGS: Diffusion-Generated Pseudo-Observations for High-Quality Sparse-View Reconstruction
Xinhang Liu, Jiaben Chen, Shiu-hong Kao +2
Novel view synthesis via Neural Radiance Fields (NeRFs) or 3D Gaussian Splatting (3DGS) typically necessitates dense observations with hundreds of input images to circumvent artifa…
Instance Neural Radiance Field
Yichen Liu, Benran Hu, Junkai Huang +2
This paper presents one of the first learning-based NeRF 3D instance segmentation pipelines, dubbed as Instance Neural Radiance Field, or Instance NeRF. Taking a NeRF pretrained fr…
Mask-Free Video Instance Segmentation
Lei Ke, Martin Danelljan, Henghui Ding +3
The recent advancement in Video Instance Segmentation (VIS) has largely been driven by the use of deeper and increasingly data-hungry transformer-based models. However, video masks…
Clean-NeRF: Reformulating NeRF to account for View-Dependent Observations
Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang
While Neural Radiance Fields (NeRFs) had achieved unprecedented novel view synthesis results, they have been struggling in dealing with large-scale cluttered scenes with sparse inp…
ONeRF: Unsupervised 3D Object Segmentation from Multiple Views
Shengnan Liang, Yichen Liu, Shangzhe Wu +2
We present ONeRF, a method that automatically segments and reconstructs object instances in 3D from multi-view RGB images without any additional manual annotations. The segmented 3…
H-VFI: Hierarchical Frame Interpolation for Videos with Large Motions
Changlin Li, Guangyang Wu, Yanan Sun +3
Capitalizing on the rapid development of neural networks, recent video frame interpolation (VFI) methods have achieved notable improvements. However, they still fall short for real…
Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts
Qi Fan, Mattia Segu, Yu-Wing Tai +4
Improving model's generalizability against domain shifts is crucial, especially for safety-critical applications such as autonomous driving. Real-world domain styles can vary subst…
SDRTV-to-HDRTV Conversion via Spatial-Temporal Feature Fusion
Kepeng Xu, Li Xu, Gang He +4
HDR(High Dynamic Range) video can reproduce realistic scenes more realistically, with a wider gamut and broader brightness range. HDR video resources are still scarce, and most vid…
NeRF-RPN: A general framework for object detection in NeRFs
Benran Hu, Junkai Huang, Yichen Liu +2
This paper presents the first significant object detection framework, NeRF-RPN, which directly operates on NeRF. Given a pre-trained NeRF model, NeRF-RPN aims to detect all boundin…
FLNeRF: 3D Facial Landmarks Estimation in Neural Radiance Fields
Hao Zhang, Tianyuan Dai, Yu-Wing Tai +1
This paper presents the first significant work on directly predicting 3D face landmarks on neural radiance fields (NeRFs). Our 3D coarse-to-fine Face Landmarks NeRF (FLNeRF) model…
Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation
Xinhang Liu, Jiaben Chen, Huai Yu +2
We present radiance field propagation (RFP), a novel approach to segmenting objects in 3D during reconstruction given only unlabeled multi-view images of a scene. RFP is derived fr…
Scene Text Image Super-Resolution via Content Perceptual Loss and Criss-Cross Transformer Blocks
Rui Qin, Bin Wang, Yu-Wing Tai
Text image super-resolution is a unique and important task to enhance readability of text images to humans. It is widely used as pre-processing in scene text recognition. However,…
DeViT: Deformed Vision Transformers in Video Inpainting
Jiayin Cai, Changlin Li, Xin Tao +2
This paper proposes a novel video inpainting method. We make three main contributions: First, we extended previous Transformers with patch alignment by introducing Deformed Patch-b…